uptaded assignment-two

02_activities/assignments/Assignment2.md

@@ -54,7 +54,30 @@ The store wants to keep customer addresses. Propose two architectures for the CU
 **HINT:** search type 1 vs type 2 slowly changing dimensions. 
 
 ```
-Your answer...
+CUSTOMER_ADDRESS table
+Architecture 1: Retaining Changes (Type2)
+customer_id (Primary Key)
+address_line1
+address_line2
+city
+province
+postal_code
+country
+updated_date
+
+Architecture 2: Retaining Changes (Type2)
+address_id (Primary Key)
+customer_id
+address_line1
+address_line2
+city
+province
+postal_code
+country
+effective_date
+end_date
+is_current
+
 ```
 
 ***

02_activities/assignments/assignment2.sql

@@ -20,6 +20,20 @@ The `||` values concatenate the columns into strings.
 Edit the appropriate columns -- you're making two edits -- and the NULL rows will be fixed. 
 All the other rows will remain the same.) */
 
+--zero problem
+SELECT 
+product_name || ', ' || product_size|| ' (' || product_qty_type || ')'
+FROM product;
+
+--first problem
+SELECT
+product_name || ',' || coalesce(product_size,'')|| ' (' ||coalesce(product_qty_type,'')|| ')' as Product_name_size_qty_type
+FROM product;
+
+--second problem
+SELECT
+product_name || ',' || coalesce(product_size,'')|| ' (' ||coalesce(product_qty_type,'unit')|| ')' as Product_name_size_qty_type
+FROM product;
 
 
 --Windowed Functions
@@ -32,17 +46,86 @@ each new market date for each customer, or select only the unique market dates p
 (without purchase details) and number those visits. 
 HINT: One of these approaches uses ROW_NUMBER() and one uses DENSE_RANK(). */
 
+--ROW-NUMBER
+SELECT*
+	,row_number() OVER(PARTITION BY customer_id ORDER BY market_date) as customer_visit_number
+
+
+FROM customer_purchases
+GROUP BY customer_id, market_date 
+ORDER BY customer_id, market_date
 
 
+--dense_rank
+SELECT
+	customer_id,
+	market_date
+	,dense_rank() OVER(PARTITION BY customer_id ORDER BY market_date) as customer_visit_number
+
+
+FROM customer_purchases
+ORDER BY customer_id, market_date;
+
 /* 2. Reverse the numbering of the query from a part so each customer’s most recent visit is labeled 1, 
 then write another query that uses this one as a subquery (or temp table) and filters the results to 
 only the customer’s most recent visit. */
 
+--ROW-NUMBER
+SELECT
+product_id,
+vendor_id,
+customer_id,
+market_date as recent_visit_market_date,
+quantity,
+cost_to_customer_per_qty,
+transaction_time,
+x.customer_visit_number
+
+FROM(
+	SELECT*
+	,row_number() OVER(PARTITION BY customer_id ORDER BY market_date DESC) as customer_visit_number
+
+
+	FROM customer_purchases
+	GROUP BY customer_id, market_date 
+	ORDER BY customer_id, market_date DESC
+)x
+
+WHERE x.customer_visit_number=1;
+
+
+--dense_rank
+SELECT
+product_id,
+vendor_id,
+customer_id,
+market_date as recent_visit_market_date,
+quantity,
+cost_to_customer_per_qty,
+transaction_time,
+x.customer_visit_number
+FROM(
+	SELECT*
+	,dense_rank() OVER(PARTITION BY customer_id ORDER BY market_date DESC) as customer_visit_number
+
+
+	FROM customer_purchases
+	ORDER BY customer_id, market_date DESC
+)x
+
+WHERE x.customer_visit_number=1;
+
 
 
 /* 3. Using a COUNT() window function, include a value along with each row of the 
 customer_purchases table that indicates how many different times that customer has purchased that product_id. */
 
+SELECT*
+,COUNT(product_id) OVER(PARTITION BY customer_id,product_id)as number_of_purchase
+FROM customer_purchases
+
+ORDER BY customer_id,product_id, market_date
+
 
 
 -- String manipulations
@@ -57,8 +140,31 @@ Remove any trailing or leading whitespaces. Don't just use a case statement for
 
 Hint: you might need to use INSTR(product_name,'-') to find the hyphens. INSTR will help split the column. */
 
+SELECT*,
+CASE
+	WHEN instr(product_name,'-') THEN
+	substr(product_name,INSTR(product_name, '-')+2)
+	ELSE  'NULL'
+
+END AS description
+
+FROM product
+
 
 
+/* 2. Filter the query to show any product_size value that contain a number with REGEXP. */
+SELECT*,
+
+CASE
+	WHEN instr(product_name,'-') THEN
+	substr(product_name,INSTR(product_name, '-')+2)
+	ELSE  'NULL'
+
+END AS description
+
+FROM product
+WHERE product_size REGEXP'^[0-9]'
+
 
 -- UNION
 /* 1. Using a UNION, write a query that displays the market dates with the highest and lowest total sales.
@@ -71,6 +177,48 @@ HINT: There are a possibly a few ways to do this query, but if you're struggling
 with a UNION binding them. */
 
 
+---1.creating a table that calculates total_sales
+DROP TABLE IF EXISTS temp.total_sales
+
+CREATE TABLE temp.total_sales AS
+SELECT*
+FROM(
+	SELECT*
+	,ROUND(SUM(quantity*cost_to_customer_per_qty),2)as total_sales
+---,ROW_NUMBER() OVER(PARTITION BY market_date ORDER BY SUM(quantity*cost_to_customer_per_qty)) AS total_sales_count 
+    --,RANK()OVER(PARTITION BY market_date ORDER BY SUM(quantity*cost_to_customer_per_qty) ) as sales_rank
+	FROM customer_purchases
+	GROUP BY market_date
+	)X
+
+---2.creating a second table that ranks sales	
+DROP TABLE IF EXISTS temp.rank_sales
+
+CREATE TABLE temp.rank_sales AS
+SELECT*
+	,RANK()OVER(ORDER BY total_sales) AS low_to_high_sale
+	,RANK()OVER (ORDER BY total_sales DESC) AS high_to_low_sale
+
+FROM temp.total_sales
+
+
+--3. creating UNION to list the highest and lowest total sales
+
+SELECT
+market_date,
+total_sales,
+high_to_low_sale as sale_rank
+FROM temp.rank_sales
+WHERE low_to_high_sale =1
+
+UNION
+
+SELECT
+market_date,
+total_sales,
+high_to_low_sale as sale_rank
+FROM temp.rank_sales
+WHERE high_to_low_sale =1
 
 
 /* SECTION 3 */
@@ -86,25 +234,65 @@ Think a bit about the row counts: how many distinct vendors, product names are t
 How many customers are there (y). 
 Before your final group by you should have the product of those two queries (x*y).  */
 
-
+SELECT
+vendor_name,
+product_name,
+SUM(product_cost) earning_per_product
+FROM(
+SELECT
+vendor_name, product_name, SUM(price)as product_cost
+FROM(
+	SELECT DISTINCT
+	vendor_name,
+	product_name,
+	5*original_price AS price
+	FROM vendor_inventory vi
+	INNER JOIN product p 
+	ON vi.product_id = p.product_id
+	INNER JOIN vendor v
+	ON v.vendor_id = vi.vendor_id
+)
+GROUP BY vendor_name, product_name)
+
+CROSS JOIN
+(SELECT DISTINCT
+customer_id
+FROM customer)
+
+GROUP BY vendor_name, product_name
 
 -- INSERT
 /*1.  Create a new table "product_units". 
 This table will contain only products where the `product_qty_type = 'unit'`. 
 It should use all of the columns from the product table, as well as a new column for the `CURRENT_TIMESTAMP`.  
 Name the timestamp column `snapshot_timestamp`. */
 
+DROP TABLE IF EXISTS temp.product_units
+
+CREATE TABLE product_units AS
+
+SELECT*
+,CURRENT_TIMESTAMP as snapshot_timestamp
+FROM product
+WHERE product_qty_type = 'unit'
+
 
 
 /*2. Using `INSERT`, add a new row to the product_units table (with an updated timestamp). 
 This can be any product you desire (e.g. add another record for Apple Pie). */
 
 
+INSERT INTO product_units
+VALUES(24, 'Cut Zinnias Bouquet', 'large',4,'unit',CURRENT_TIMESTAMP)
+
 
 -- DELETE
 /* 1. Delete the older record for the whatever product you added. 
 
 HINT: If you don't specify a WHERE clause, you are going to have a bad time.*/
+DELETE
+FROM product_units
+WHERE product_id=6
 
 
 
@@ -125,6 +313,30 @@ Finally, make sure you have a WHERE statement to update the right row,
 	you'll need to use product_units.product_id to refer to the correct row within the product_units table. 
 When you have all of these components, you can run the update statement. */
 
+ALTER TABLE product_units
+ADD current_quantity INT;
+
+---updating the product table
+UPDATE product_units
+SET current_quantity =
+	(SELECT current_quantity
+
+	FROM(
+	SELECT
+	pu.product_id,
+	coalesce(quantity,0) as current_quantity
+	FROM product_units as pu
+
+	LEFT JOIN(
+	SELECT*
+	,row_number()over(partition by vi.product_id order by market_date DESC) as date_row_number
+	from vendor_inventory as vi
+	)y
+	ON y.product_id = pu.product_id
+	WHERE date_row_number =1 OR date_row_number IS NULL
+
+)x
+WHERE x.product_id =product_units.product_id)